Method, device and equipment for matching electronic map data and map collection data

Abstract

Embodiments of the present specification disclose a kind of electronic map data and the matching method, device and equipment of map acquisition data.The scheme can include: obtaining the map acquisition data of map data acquisition equipment acquisition;According to the related data of the first map element at target road section in map acquisition data, and the related data of the second map element at target road section in electronic map data, determine map element data set;According to map element data set, construct undirected weighted graph;From undirected weighted graph, determine the first target complete subgraph of the maximum sum of weight value, obtain the matching result between electronic map data and map acquisition data.Such, improve the accuracy of the matching result of map acquisition data and electronic map data, reduce the dependency of the accuracy of matching result on the absolute accuracy of map data acquisition equipment acquisition.

Description

Technical Field

[0001] This application relates to the field of high-precision map technology, and in particular to a method, apparatus and equipment for matching electronic map data and map acquisition data. Background Technology

[0002] Electronic maps, also known as digital maps, are maps stored and viewed digitally using computer technology. High-precision electronic maps, including high-resolution maps, provide crucial technical support for autonomous driving. To ensure the real-time nature of electronic maps, they need to be updated regularly.

[0003] Currently, high-precision maps are updated based on high-precision crowdsourced map data. In the process of updating high-precision maps using this data, for each map element in the high-precision map, the target map data corresponding to that map element is determined from the map data collected by the map data acquisition device, and the corresponding map element in the high-precision map is updated based on this target map data.

[0004] However, in related technologies, map data matching is based solely on the absolute accuracy of the map data acquisition equipment. This results in low accuracy when the absolute accuracy of the equipment is low, leading to lower accuracy in the matching between the acquired map data and the electronic map data of the high-precision map. This, in turn, affects the accuracy of the high-precision map update. Absolute accuracy refers to the degree of difference between the location data of a map feature acquired by the map data acquisition equipment and the actual location data of that feature. Summary of the Invention

[0005] This specification provides a method, apparatus, and device for matching electronic map data with map-collected data, in order to solve the technical problems of low accuracy in matching results between map-collected data and electronic map data, and the fact that the accuracy of the matching results depends on the absolute precision of the map data collection equipment.

[0006] To solve the above-mentioned technical problems, the embodiments in this specification are implemented as follows:

[0007] This specification provides an embodiment of a method for matching electronic map data with map-collected data, including:

[0008] Acquire map data collected by map data acquisition devices;

[0009] Based on the relevant data of the first map element at the target road segment in the map collection data and the relevant data of the second map element at the target road segment in the electronic map data, a map element data set is determined;

[0010] Based on the map feature data set, an undirected weighted graph is constructed; the weight values ​​of the vertices in the undirected weighted graph are used to reflect the similarity between the first map feature corresponding to the vertex and the second map feature corresponding to the vertex; the connecting edges of the undirected weighted graph are used to reflect the difference between the positional relationships of the map features corresponding to the two vertices of the connecting edge, which is within a preset difference range; the positional relationship of the map features is the positional relationship between the first map feature corresponding to any vertex and the second map feature corresponding to any vertex;

[0011] From the undirected weighted graph, the first target complete subgraph with the largest sum of weight values ​​is determined, and the matching result between the electronic map data and the map collection data is obtained.

[0012] This specification provides an embodiment of a device for matching electronic map data with map-collected data, comprising:

[0013] The map data acquisition module is used to acquire map data collected by the map data acquisition device.

[0014] The map element data set determination module is used to determine the map element data set based on the relevant data of the first map element at the target road segment in the map collection data and the relevant data of the second map element at the target road segment in the electronic map data.

[0015] An undirected weighted graph construction module is used to construct an undirected weighted graph based on the map feature data set. The weight values ​​of the vertices in the undirected weighted graph are used to reflect the similarity between the first map feature corresponding to the vertex and the second map feature corresponding to the vertex. The connecting edges of the undirected weighted graph are used to reflect that the difference between the positional relationships of the map features corresponding to the two vertices of the connecting edge is within a preset difference range. The positional relationship of the map features is the positional relationship between the first map feature corresponding to any vertex and the second map feature corresponding to any vertex.

[0016] The first target complete subgraph determination module is used to determine the first target complete subgraph with the largest sum of weight values ​​from the undirected weighted graph, and obtain the matching result between the electronic map data and the map collection data.

[0017] This specification provides an embodiment of a device for matching electronic map data with map-collected data, comprising:

[0018] At least one processor; and,

[0019] A memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores instructions that can be executed by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to:

[0021] Acquire map data collected by map data acquisition devices;

[0022] Based on the relevant data of the first map element at the target road segment in the map collection data and the relevant data of the second map element at the target road segment in the electronic map data, a map element data set is determined;

[0023] Based on the map feature data set, an undirected weighted graph is constructed; the weight values ​​of the vertices in the undirected weighted graph are used to reflect the similarity between the first map feature corresponding to the vertex and the second map feature corresponding to the vertex; the connecting edges of the undirected weighted graph are used to reflect the difference between the positional relationships of the map features corresponding to the two vertices of the connecting edge, which is within a preset difference range; the positional relationship of the map features is the positional relationship between the first map feature corresponding to any vertex and the second map feature corresponding to any vertex;

[0024] From the undirected weighted graph, the first target complete subgraph with the largest sum of weight values ​​is determined, and the matching result between the electronic map data and the map collection data is obtained.

[0025] At least one embodiment provided in this specification can achieve the following beneficial effects: After acquiring map acquisition data collected by a map data acquisition device, a map element data set is determined based on the relevant data of the first map element at the target road segment in the map acquisition data and the relevant data of the second map element at the target road segment in the electronic map data; an undirected weighted graph is constructed based on the map element data set; the weight value of the vertices of the undirected weighted graph is used to reflect the similarity between the first map element corresponding to the vertex and the second map element corresponding to the vertex; the connecting edges of the undirected weighted graph are used to reflect the difference between the positional relationships of the map elements of the two vertices corresponding to the connecting edges being within a preset difference range; the positional relationship of the map elements is the positional relationship between the first map element corresponding to any vertex and the second map element corresponding to any vertex; from the undirected weighted graph, the first target complete subgraph with the largest sum of weight values ​​is determined, and the matching result between the electronic map data and the map acquisition data is obtained. Based on this, this method constructs an undirected weighted graph, transforming the process of determining the optimal matching result into the process of determining the complete subgraph with the largest sum of weight values. This allows the application to comprehensively consider all matching results, improving the accuracy of the matching results between map-collected data and electronic map data. Furthermore, since the connecting edges of the undirected weighted graph can reflect the difference between the positional relationships of map features at the two vertices corresponding to the connecting edges, which is within a preset difference range, this application can ensure the accuracy of the matching results even when the absolute accuracy of the map data collection equipment is low. This reduces the dependence on the absolute accuracy of the map data collection equipment, thereby improving the accuracy of the matching results between map-collected data and electronic map data when the absolute accuracy of the map data collection equipment is low. At the same time, when the absolute accuracy of the map data collection equipment is high, it can further improve the accuracy of the matching results between map-collected data and electronic map data. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 A flowchart illustrating a method for matching electronic map data with map-collected data, provided in an embodiment of this specification;

[0028] Figure 2 A schematic diagram of vertex construction provided in an embodiment of this specification;

[0029] Figure 3 A schematic diagram of the structure of a matching device for electronic map data and map acquisition data provided in the embodiments of this specification;

[0030] Figure 4 This is a schematic diagram of the structure of a matching device for electronic map data and map acquisition data provided in an embodiment of this specification. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of one or more embodiments of this specification clearer, the technical solutions of one or more embodiments of this specification will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of them. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of one or more embodiments of this specification.

[0032] The technical solutions provided in the various embodiments of this specification are described in detail below with reference to the accompanying drawings.

[0033] Figure 1 This is a flowchart illustrating a method for matching electronic map data with map-collected data, as described in an embodiment of this specification. From a device perspective, the entity executing this process can be a server; from a program perspective, the entity executing this process can be an application program installed on the server for matching electronic map data with map-collected data. Figure 1 As shown, the process may include the following steps:

[0034] Step 101: Obtain map data collected by the map data collection device.

[0035] Specifically, map-collected data refers to vector semantic data generated from map data collected by map data collection equipment. It includes location data and semantic data of map features. Semantic data is used to reflect the attributes of map features, such as the feature type (e.g., a straight ground arrow or a left-turn ground arrow), the color of the map feature, and the width value of the map feature.

[0036] In practical applications, map data acquisition equipment is often installed on vehicles, which travel along the roads to be collected. During the journey, the map data acquisition equipment collects relevant data of the map features it passes by.

[0037] Step 102: Determine the map element data set based on the relevant data of the first map element at the target road segment in the map collection data and the relevant data of the second map element at the target road segment in the electronic map data.

[0038] In detail, since the amount of map data collected each time is often large, to improve matching efficiency, relevant data of the first map element at the target road segment can be selected from the map data collection, and relevant data of the second map element at the target road segment can be selected from the electronic map data to form a map element data set. Based on this map element data set, the electronic map data and the map data collection are then matched. The electronic map data can be relevant data from a high-precision map stored in a pre-set database.

[0039] Step 103: Construct an undirected weighted graph based on the map feature data set; for each vertex of the undirected weighted graph, the first map feature corresponding to the vertex is matched with the second map feature corresponding to the vertex, and the weight value of the vertex is used to reflect the similarity between the first map feature corresponding to the vertex and the second map feature corresponding to the vertex; for each connecting edge of the undirected weighted graph, the connecting edge is used to reflect that the difference between the positional relationship of the map features of the two vertices corresponding to the connecting edge is within a preset difference range; the positional relationship of the map features is the positional relationship between the first map feature corresponding to any vertex and the second map feature corresponding to any vertex.

[0040] In practical applications, the first step is to construct the vertices of the undirected weighted graph. The construction method for each vertex of the undirected weighted graph is the same; the construction method for any vertex of the undirected weighted graph can be:

[0041] For any first map feature, a target second map feature of the same feature type as the first map feature is determined from the second map features; if the distance between the first map feature and any target second map feature is within a preset distance range, then a vertex in the undirected weighted graph is constructed using the first map feature and the target second map feature.

[0042] The preset distance range represents the absolute accuracy requirement of the map data acquisition device in this method. For example, when the preset distance range is set to 0-30 meters, map data acquired by map data acquisition devices with an absolute accuracy within 0-30 meters can be used in this embodiment. This reduces the number of vertices in the undirected weighted graph, improves matching efficiency, and ensures the accuracy of the matching results.

[0043] In practical applications, after obtaining the map feature data set, each first map feature in the data set is traversed. When any first map feature (let's say R1) is encountered, a target second map feature of the same type as R1 is identified in the data set (at least one target second map feature is required). Then, based on the location data of the map features in the data set, the distance between the first map feature R1 and any target second map feature (let's say M1) is calculated. If this distance is within a preset distance range, a vertex (R1, M1) is constructed using the first map feature R1 and the second map feature M1 in an undirected weighted graph.

[0044] To illustrate the above scheme in more detail, examples are given below. Figure 2 This is a schematic diagram of vertex construction provided for an embodiment of this specification. Figure 2 As shown in the figure, the solid line represents a ground marking collected by the map data acquisition device, and the dashed line represents a ground marking in the electronic map data. If the calculated distance between the two ground markings is within a preset distance range, then a vertex in an undirected weighted graph can be constructed using the two ground markings.

[0045] Then, construct the connecting edges of the undirected weighted graph. The construction method for each connecting edge of the undirected weighted graph is the same; the construction method for any connecting edge of the undirected weighted graph can be:

[0046] For each vertex in the undirected weighted graph, if the first map feature corresponding to the vertex is a point feature, then the lateral directed distance and the longitudinal directed distance between the first map feature corresponding to the vertex and the second map feature corresponding to the vertex are determined based on the relevant data of the first map feature corresponding to the vertex and the relevant data of the second map feature corresponding to the vertex; if the first map feature corresponding to the vertex is a line feature, then the lateral directed distance between the first map feature corresponding to the vertex and the second map feature corresponding to the vertex is determined based on the relevant data of the first map feature corresponding to the vertex and the relevant data of the second map feature corresponding to the vertex.

[0047] Then, for any two vertices in the undirected weighted graph, if at least one of the two vertices corresponds to a first map feature that is a line feature, it is determined whether the difference between the lateral directed distances corresponding to the two vertices is within a first preset difference range. If the difference between the lateral directed distances corresponding to the two vertices is within the first preset difference range, a connecting edge is constructed between the two vertices. Furthermore, if the first map features corresponding to the two vertices are both point features, it is determined whether the difference between the lateral directed distances corresponding to the two vertices is within the first preset difference range, and whether the difference between the longitudinal directed distances corresponding to the two vertices is within a second preset difference range. If the difference between the lateral directed distances corresponding to the two vertices is within the first preset difference range, and the difference between the longitudinal directed distances corresponding to the two vertices is within the second preset difference range, a connecting edge is constructed between the two vertices.

[0048] To illustrate the above scheme in more detail, an example is given below. Assume vertices V1 (R1, M1) and V2 (R2, M2) are any two vertices in an undirected weighted graph, and R1 and R2 are both first-level map features of point type, while M1 and M2 are both second-level map features of point type. In constructing a connecting edge of the undirected weighted graph using vertices V1 (R1, M1) and V2 (R2, M2), the following steps can be taken: First, calculate the lateral directed distance of vertex V1 (R1, M1). Specifically, subtract the lateral coordinates of second-level map feature M1 from the lateral coordinates of first-level map feature R1 to obtain the lateral directed distance D1. Next, calculate the lateral directed distance of vertex V2 (R2, M2). Specifically, subtract the lateral coordinates of second-level map feature M2 from the lateral coordinates of first-level map feature R2 to obtain the lateral directed distance D2. Then, calculate the absolute value of the difference between lateral directed distances D1 and D2, i.e., |D1-D2|. Simultaneously, the directed vertical distance of vertex V1 (R1, M1) is calculated. Specifically, the directed vertical distance d1 is obtained by subtracting the directed vertical coordinate of the second map element M1 from the directed vertical coordinate of the first map element R1. Next, the directed vertical distance of vertex V2 (R2, M2) is calculated. Specifically, the directed vertical distance d2 is obtained by subtracting the directed vertical coordinate of the second map element M2 from the directed vertical coordinate of the first map element R2. Then, the absolute value of the difference between the directed vertical distances d1 and d2, i.e., |d1-d2|, is calculated. Finally, if it is determined that the absolute value |d1-d2| is within a first preset difference range and the absolute value |d1-d2| is within a second preset difference range, then an undirected weighted graph connection edge is constructed between vertex V1 (R1, M1) and vertex V2 (R2, M2).

[0049] It should be noted that the horizontal direction is perpendicular to the direction of travel on the road, and the vertical direction is parallel to the direction of travel on the road.

[0050] Furthermore, after constructing the vertices of the undirected weighted graph, the weight value of each vertex can be determined. The method for determining the weight value of each vertex in an undirected weighted graph is the same; the method for determining the weight value of any given vertex can be:

[0051] For any vertex in the undirected weighted graph, calculate the similarity of map feature attributes between the first map feature corresponding to the vertex and the second map feature corresponding to the vertex; then, calculate the importance value of the vertex based on at least one of the category and length of the second map feature corresponding to the vertex; finally, calculate the product of the map feature attribute similarity and the importance value to obtain the weight value of the vertex.

[0052] Preferably, calculating the similarity of map feature attributes between the first map feature corresponding to the vertex and the second map feature corresponding to the vertex may specifically include:

[0053] The target attributes of the first map element corresponding to the vertex are determined; then, for each target attribute, a preset attribute similarity calculation rule corresponding to the type of the target attribute is used to calculate the target attribute similarity; finally, the average value of the target attribute similarities is calculated to obtain the map element attribute similarity between the first map element corresponding to the vertex and the second map element corresponding to the vertex.

[0054] Preferably, the step of calculating the target attribute similarity using a preset attribute similarity calculation rule corresponding to the type of the target attribute specifically includes:

[0055] If the target attribute is a continuous attribute, then the first target attribute similarity is determined based on the map feature similarity between the first map feature corresponding to the vertex and the second map feature corresponding to the vertex; the map feature similarity is positively correlated with the first target attribute similarity.

[0056] If the target attribute is a discrete attribute, then the second target attribute similarity is determined based on the feature type of the first map feature corresponding to the vertex and the feature type of the second map feature corresponding to the vertex; when the second target attribute similarity is a first preset value, the feature type of the first map feature corresponding to the vertex is the same as the feature type of the second map feature corresponding to the vertex; when the second target attribute similarity is a second preset value, the feature type of the first map feature corresponding to the vertex is different from the feature type of the second map feature corresponding to the vertex.

[0057] In practical applications, if the target attribute is a continuous attribute, the similarity of the target attribute can be calculated according to the following formula:

[0058]

[0059] Among them, R i M is the first map element. i For the second map element; similarity 连续 (R i M i ) represents the similarity of the target attributes, attributevalue(R) i ) represents the attribute value of the first map feature; attributevalue(Mi ) represents the attribute value of the second map element.

[0060] To illustrate the calculation formula in more detail, an example is given below. For instance, the first and second map features corresponding to a certain vertex are both ground markings. For a ground marking, its attribute includes width. The method for calculating the target attribute similarity corresponding to this width attribute for that vertex is as follows:

[0061]

[0062] Among them, S 宽度 The similarity of the target attribute corresponding to the width attribute of the first map element.

[0063] Secondly, if the target attribute is a discrete attribute, the target attribute similarity can be calculated using the following formula:

[0064]

[0065] Following the example above, the attributes of ground markings can also include color and marking type. The similarity of the target attributes corresponding to the color attribute is as follows:

[0066]

[0067] Among them, S 颜色 This represents the similarity of the target attributes to the color attributes of the first map element.

[0068] The similarity of target attributes corresponding to the marking types is as follows:

[0069]

[0070] Among them, S 类型 The similarity of the target attributes corresponding to the line type attribute of the first map element.

[0071] Finally, after determining the target attribute similarity corresponding to each attribute of the ground markings, S is calculated. 宽度 S 颜色 and S 类型 The average value (i.e., S) 宽度 +S 颜色 +S 类型 ) / 3), to obtain the similarity of map feature attributes of the vertex.

[0072] Preferably, calculating the importance value of the vertex based on at least one of the category and length of the second map feature corresponding to the vertex specifically includes:

[0073] Determine whether the first map element corresponding to the vertex is a point element; if the first map element corresponding to the vertex is a point element, then determine the importance value of the vertex as a third preset value; if the first map element corresponding to the vertex is not a point element, then determine the importance value of the vertex based on the element length of the second map element corresponding to the vertex; the element length of the second map element corresponding to the vertex is positively correlated with the importance value of the vertex.

[0074] In practical applications, the importance value of a vertex can be calculated using the following formula:

[0075]

[0076] Where, length(R) i M i ) represents the importance value of the vertex; UNIT is a preset constant, which can be set to 100, 200, 300, etc., in meters.

[0077] Step 104: From the undirected weighted graph, determine the first target complete subgraph with the largest sum of weight values, and obtain the matching result between the electronic map data and the map collection data.

[0078] Specifically, each complete subgraph of an undirected weighted graph represents a matching result, and the greater the sum of the weight values ​​of the complete subgraphs, the higher the accuracy of the matching result corresponding to that complete subgraph. After determining the complete subgraph with the largest sum of weight values, the matching result corresponding to that complete subgraph can be determined based on the vertices contained in that complete subgraph.

[0079] This embodiment employs the aforementioned technical solution. After acquiring map data collected by the map data acquisition device, a map element data set is determined based on the relevant data of the first map element at the target road segment in the map data acquisition data and the relevant data of the second map element at the target road segment in the electronic map data. An undirected weighted graph is constructed based on this map element data set. For each vertex of the undirected weighted graph, the first map element corresponding to the vertex is matched with the second map element corresponding to the vertex, and the vertex's weight value reflects the similarity between the first and second map elements corresponding to the vertex. For each connecting edge of the undirected weighted graph, the connecting edge reflects that the difference between the positional relationships of the map elements corresponding to the two vertices of the connecting edge is within a preset difference range. The positional relationship of the map elements is the positional relationship between the first map element corresponding to any vertex and the second map element corresponding to any vertex. From the undirected weighted graph, the first target complete subgraph with the largest sum of weight values ​​is determined, thus obtaining the matching result between the electronic map data and the map data acquisition data. Based on this, this method transforms the process of determining the optimal matching result into the process of determining the complete subgraph with the largest sum of weight values. This allows the application to comprehensively consider all matching results, improving the accuracy of the matching results between map-collected data and electronic map data. Furthermore, since the connecting edges of an undirected weighted graph can be used to reflect the difference between the positional relationships of map features at the two vertices corresponding to the connecting edges, which is within a preset difference range, this application can ensure the accuracy of the matching results even when the absolute accuracy of the map data collection equipment is low. This reduces the dependence on the absolute accuracy of the map data collection equipment, thereby improving the accuracy of the matching results between map-collected data and electronic map data when the absolute accuracy of the map data collection equipment is low. At the same time, when the absolute accuracy of the map data collection equipment is high, it can further improve the accuracy of the matching results between map-collected data and electronic map data.

[0080] Preferably, step 104, determining the first target complete subgraph with the largest sum of weight values ​​from the undirected weighted graph, may specifically include:

[0081] Obtain each complete subgraph in the undirected weighted graph.

[0082] Determine the sum of the weight values ​​of each vertex corresponding to each complete subgraph.

[0083] From the complete subgraphs, determine the first target complete subgraph with the largest sum of weight values.

[0084] Specifically, after obtaining the undirected weighted graph, its complete subgraphs are obtained by recursively traversing the graph. The recursive traversal process is as follows:

[0085] Initialize the set P as the set of all vertices of an undirected weighted graph.

[0086] Calculate the sum of the weights of each vertex in set P to obtain the target weight sum.

[0087] Initialize the R set to an empty set.

[0088] Based on a preset partitioning rule, the vertices in set P are sequentially partitioned into bifurcation subsets. The preset partitioning rule is as follows: for each first vertex in set P, if the first vertex is not directly connected to any vertex in the bifurcation subset when the bifurcation subset is not empty, and if the bifurcation subset is empty, the first vertex is partitioned into the bifurcation subset. Conversely, if the first vertex is directly connected to at least one vertex in the bifurcation subset, that first vertex is skipped, and the partitioning continues to the next first vertex, until all first vertices are partitioned. The initial state of the bifurcation subset is empty.

[0089] Determine if the bifurcation subset is empty; if it is empty, construct a complete subgraph of the undirected weighted graph based on the vertices in set R.

[0090] If the bifurcation subset is not empty, then for each second vertex in the bifurcation subset, perform the following iterative process:

[0091] The second vertex is assigned to set R to update set R.

[0092] Remove the second vertex from set P, as well as any vertices not connected to the second vertex, to obtain the updated set P.

[0093] Calculate the sum of the weights of all vertices in set P to obtain the current sum of weights.

[0094] If the sum of the current weight values ​​exceeds the sum of the target weight values, then the sum of the target weight values ​​is updated based on the sum of the current weight values.

[0095] Determine whether the sum of the weights of the target set is less than half of the sum of the target weights; the target set is a set consisting of set R and set P.

[0096] If the sum of the weights of the target set is less than half of the sum of the target weights, then the loop process for the second vertex ends.

[0097] If the sum of the weights of the target set is not less than half of the sum of the target weights, then proceed to step: Based on the preset partitioning rules, divide the vertices in set P into the bifurcation subsets in sequence until the loop process for the second vertex is completed.

[0098] Preferably, after initializing the P set as a set of vertices of an undirected weighted graph, the method in this embodiment may further include:

[0099] For each vertex in the undirected weighted graph, calculate the number of target vertices connected to that vertex.

[0100] Based on the number of target vertices of each vertex in the set P, the vertices in the set P are sorted according to the sorting rule of the number of target vertices from largest to smallest. During the sorting process, if at least two vertices have the same number of target vertices, then the at least two vertices are sorted according to the order of their weight values ​​from largest to smallest, and finally the sorting result is obtained.

[0101] The step of dividing the vertices in the set P into bifurcation subsets based on a preset partitioning rule may specifically include:

[0102] Based on the preset partitioning rules, the vertices in the P set are sequentially divided into bifurcation subsets according to the sorting results.

[0103] Preferably, after step 103, constructing an undirected weighted graph based on the map feature data set, the method of this embodiment may further include:

[0104] From the undirected weighted graph, a second target complete subgraph is determined; the second target complete subgraph is a complete subgraph of the undirected weighted graph whose sum of weight values ​​is only less than that of the first target complete subgraph.

[0105] Based on preset evaluation criteria, an evaluation result is obtained for the first target complete sub-map according to the first target complete sub-map and the second target complete sub-map; the evaluation result is used to reflect the difference in the sum of weight values ​​between the first target complete sub-map and the second target complete sub-map, as well as the difference between the number of the first map elements contained in the first target complete sub-map and the number of the first map elements contained in the map acquisition data.

[0106] In practical applications, after obtaining all complete subgraphs of the undirected weighted graph, the sum of the weights of each vertex in each complete subgraph is calculated to obtain the sum of the weights of that complete subgraph. Then, the complete subgraphs are sorted in descending order of the sum of their weights, with the first complete subgraph being the first target complete subgraph and the second complete subgraph being the second target complete subgraph.

[0107] Then, the difference between the sum of the weight values ​​of the first target complete subgraph and the second target complete subgraph is calculated according to the following formula:

[0108]

[0109] Here, accuracy1 represents the difference between the sum of the weight values ​​of the first target complete subgraph and the second target complete subgraph.

[0110] Furthermore, the difference between the number of first map features contained in the first target complete submap and the number of first map features contained in the map acquisition data is calculated according to the following formula:

[0111]

[0112] Here, accuracy2 represents the degree of difference between the number of first map features contained in the first target complete submap and the number of first map features contained in the map acquisition data.

[0113] Finally, the matching accuracy of the first target complete sub-graph is calculated according to the following formula:

[0114]

[0115] The higher the matching accuracy of the first target complete subgraph, the higher the accuracy of the matching result. This embodiment quantifies the accuracy of the matching result, thus providing a reference for the accuracy of the matching result when using it subsequently.

[0116] Preferably, step 102 may specifically include:

[0117] The map data is matched with the electronic map data to determine the driving route of the map data collection device.

[0118] The driving road is divided into multiple road segments.

[0119] For any one of the roads, the relevant data of the first map element at any one of the roads in the map collection data and the relevant data of the second map element at any one of the roads in the electronic map data are divided into the map element data set.

[0120] Specifically, the map data acquisition data and the electronic map data can be input into a Hidden Markov Model (HMM) to obtain the driving roads of the map data acquisition device. Then, the driving roads are averaged to obtain multiple road segments. Next, for any given road, a first map feature located at that road is determined from the map data acquisition data, and a second map feature located at that road is determined from the electronic map data. Finally, the relevant data of the first map feature in the map data acquisition data and the relevant data of the second map feature in the electronic map data are assigned to the map feature data set.

[0121] Based on the same idea, embodiments of this specification also provide apparatus corresponding to the above methods. Figure 3 This is a schematic diagram of a device for matching electronic map data and map-collected data, provided as an embodiment of this specification. Figure 3 As shown, the device includes: a map data acquisition module 31, a map feature data set determination module 32, an undirected weighted graph construction module 33, and a first target complete sub-graph determination module 34.

[0122] Among them, the map data acquisition module 31 is used to acquire map data collected by the map data acquisition device.

[0123] The map element data set determination module 32 is used to determine the map element data set based on the relevant data of the first map element at the target road segment in the map collection data and the relevant data of the second map element at the target road segment in the electronic map data.

[0124] The undirected weighted graph construction module 33 is used to construct an undirected weighted graph based on the map feature data set. For each vertex of the undirected weighted graph, the first map feature corresponding to the vertex is matched with the second map feature corresponding to the vertex, and the weight value of the vertex is used to reflect the similarity between the first map feature corresponding to the vertex and the second map feature corresponding to the vertex. For each connecting edge of the undirected weighted graph, the connecting edge is used to reflect that the difference between the positional relationship of the map features of the two vertices corresponding to the connecting edge is within a preset difference range. The positional relationship of the map features is the positional relationship between the first map feature corresponding to any vertex and the second map feature corresponding to any vertex.

[0125] The first target complete subgraph determination module 34 is used to determine the first target complete subgraph with the largest sum of weight values ​​from the undirected weighted graph, and obtain the matching result between the electronic map data and the map collection data.

[0126] Preferably, the undirected weighted graph construction module 33 can be used specifically for:

[0127] For any first map feature, a target second map feature of the same feature type as the first map feature is determined from the second map features; if the distance between the first map feature and any target second map feature is within a preset distance range, then a vertex in the undirected weighted graph is constructed using the first map feature and the target second map feature.

[0128] Preferably, the undirected weighted graph construction module 33 can be used specifically for:

[0129] For each vertex in the undirected weighted graph, the directed distance between the first map element corresponding to the vertex and the second map element corresponding to the vertex is determined based on the relevant data of the first map element corresponding to the vertex and the relevant data of the second map element corresponding to the vertex.

[0130] For any two vertices in the undirected weighted graph, if the difference between the directed distances corresponding to the two vertices is within the preset difference range, then a connecting edge is constructed between the two vertices.

[0131] Preferably, the undirected weighted graph construction module 33 may specifically include:

[0132] The map feature attribute similarity determination submodule is used to calculate the map feature attribute similarity between the first map feature corresponding to the vertex and the second map feature corresponding to the vertex for any vertex in the undirected weighted graph.

[0133] The importance value determination submodule is used to calculate the importance value of the vertex based on at least one of the category and length of the second map element corresponding to the vertex.

[0134] The weight value determination submodule is used to calculate the product of the similarity of the map feature attributes and the importance value to obtain the weight value of the vertex.

[0135] Preferably, the submodule for determining the similarity of map feature attributes may specifically include:

[0136] The target attribute determination unit is used to determine the target attributes of the first map element corresponding to the vertex.

[0137] The target attribute similarity determination unit is used to calculate the target attribute similarity for each target attribute by using a preset attribute similarity calculation rule corresponding to the type of the target attribute.

[0138] The map feature attribute similarity determination unit is used to calculate the average value of the target attribute similarity of the target attribute, and obtain the map feature attribute similarity between the first map feature corresponding to the vertex and the second map feature corresponding to the vertex.

[0139] Preferably, the target attribute similarity determination unit can be used for:

[0140] If the target attribute is a continuous attribute, then the first target attribute similarity is determined based on the map feature similarity between the first map feature corresponding to the vertex and the second map feature corresponding to the vertex; the map feature similarity is positively correlated with the first target attribute similarity.

[0141] If the target attribute is a discrete attribute, then the second target attribute similarity is determined based on the feature type of the first map feature corresponding to the vertex and the feature type of the second map feature corresponding to the vertex; when the second target attribute similarity is a first preset value, the feature type of the first map feature corresponding to the vertex is the same as the feature type of the second map feature corresponding to the vertex; when the second target attribute similarity is a second preset value, the feature type of the first map feature corresponding to the vertex is different from the feature type of the second map feature corresponding to the vertex.

[0142] The importance value determination submodule can be used for:

[0143] Determine whether the first map element corresponding to the vertex is a point element.

[0144] If the first map element corresponding to the vertex is a point element, then the importance value of the vertex is determined to be a third preset value.

[0145] If the first map feature corresponding to the vertex is not a point feature, then the importance value for the vertex is determined based on the feature length of the second map feature corresponding to the vertex; the feature length of the second map feature corresponding to the vertex is positively correlated with the importance value of the vertex.

[0146] Preferably, the first target complete subgraph determination module 34 may specifically include:

[0147] The complete subgraph determination submodule is used to obtain each complete subgraph in the undirected weighted graph.

[0148] The weight sum determination submodule is used to determine the sum of the weight values ​​of each vertex corresponding to each complete subgraph.

[0149] The first target complete subgraph determination submodule is used to determine the first target complete subgraph with the largest sum of weight values ​​from the complete subgraphs.

[0150] Preferably, the complete subgraph determination submodule can be used for:

[0151] For each vertex in the undirected weighted graph, the number of target vertices connected to the vertex is calculated; based on the number of target vertices connected to the vertex and the weight value of the vertex, the visiting order of the vertex relative to other vertices in the target set is determined; the target set is a set composed of all the vertices in the undirected weighted graph; based on the visiting order, each complete subgraph in the undirected weighted graph is obtained according to each vertex in the target set.

[0152] Preferably, the apparatus of this embodiment may further include:

[0153] The evaluation result is used to determine a second target complete subgraph from the undirected weighted graph; the second target complete subgraph is a complete subgraph in which the sum of weight values ​​is only less than that of the first target complete subgraph; then, based on a preset evaluation standard, an evaluation result is obtained for the first target complete subgraph according to the first target complete subgraph and the second target complete subgraph; the evaluation result is used to reflect the difference in the sum of weight values ​​between the first target complete subgraph and the second target complete subgraph, and the difference between the number of the first map elements contained in the first target complete subgraph and the number of the first map elements contained in the map acquisition data.

[0154] Module 32 for determining map feature data sets is specifically used for:

[0155] The map data is matched with the electronic map data to determine the driving route of the map data collection device.

[0156] The driving road is divided into multiple road segments.

[0157] For any one of the roads, the relevant data of the first map element at any one of the roads in the map collection data and the relevant data of the second map element at any one of the roads in the electronic map data are divided into the map element data set.

[0158] Based on the same idea, this specification also provides devices corresponding to the above methods in its embodiments.

[0159] Figure 4 This is a schematic diagram of a device for matching electronic map data and map-collected data, provided as an embodiment of this specification. Figure 4 As shown, device 400 may include:

[0160] At least one processor 410; and,

[0161] Memory 430 communicatively connected to the at least one processor; wherein,

[0162] The memory 430 stores instructions 420 that can be executed by the at least one processor 410, the instructions being executed by the at least one processor 410 to enable the at least one processor 410 to:

[0163] Acquire map data collected by map data acquisition devices.

[0164] Based on the relevant data of the first map element at the target road segment in the map collection data and the relevant data of the second map element at the target road segment in the electronic map data, a map element data set is determined;

[0165] Based on the map feature data set, an undirected weighted graph is constructed. For each vertex of the undirected weighted graph, the first map feature corresponding to the vertex is matched with the second map feature corresponding to the vertex, and the weight value of the vertex is used to reflect the similarity between the first map feature corresponding to the vertex and the second map feature corresponding to the vertex. For each connecting edge of the undirected weighted graph, the connecting edge is used to reflect that the difference between the positional relationships of the map features of the two vertices corresponding to the connecting edge is within a preset difference range. The positional relationship of the map features is the positional relationship between the first map feature corresponding to any vertex and the second map feature corresponding to any vertex.

[0166] From the undirected weighted graph, the first target complete subgraph with the largest sum of weight values ​​is determined, and the matching result between the electronic map data and the map collection data is obtained.

[0167] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on its differences from other embodiments. In particular, for... Figure 4 As the device shown is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0168] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many methodological improvements today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that a methodological improvement cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program a digital system themselves to "integrate" it onto a PLD, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must also be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0169] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0170] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0171] For ease of description, the above devices are described separately by function as various units. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware.

[0172] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0173] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0174] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0175] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0176] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0177] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0178] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital character versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0179] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0180] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0181] This application can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0182] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for matching electronic map data with map-collected data, characterized in that, include: Acquire map data collected by map data acquisition devices; Based on the relevant data of the first map element at the target road segment in the map collection data and the relevant data of the second map element at the target road segment in the electronic map data, a map element data set is determined; Based on the map feature data set, an undirected weighted graph is constructed; the weight values ​​of the vertices in the undirected weighted graph are used to reflect the similarity between the first map feature corresponding to the vertex and the second map feature corresponding to the vertex; the connecting edges of the undirected weighted graph are used to reflect the difference between the positional relationships of the map features corresponding to the two vertices of the connecting edge, which is within a preset difference range; the positional relationship of the map features is the positional relationship between the first map feature corresponding to any vertex and the second map feature corresponding to any vertex; From the undirected weighted graph, the first target complete subgraph with the largest sum of weight values ​​is determined, and the matching result between the electronic map data and the map collection data is obtained. The first target complete subgraph is a complete subgraph of the undirected weighted graph, and there is a connecting edge between any two vertices in the complete subgraph.

2. The method according to claim 1, characterized in that, The step of constructing an undirected weighted graph based on the map feature data set specifically includes: For any one of the first map features, a target second map feature of the same feature type as the first map feature is determined from the second map features; If the distance between the first map feature and any of the target second map features is within a preset distance range, then a vertex in the undirected weighted graph is constructed using the first map feature and the target second map feature.

3. The method according to claim 2, characterized in that, The step of constructing an undirected weighted graph based on the map feature data set specifically includes: For each vertex in the undirected weighted graph, the directed distance between the first map element corresponding to the vertex and the second map element corresponding to the vertex is determined based on the relevant data of the first map element corresponding to the vertex and the relevant data of the second map element corresponding to the vertex. For any two vertices in the undirected weighted graph, if the difference between the directed distances corresponding to the two vertices is within the preset difference range, then a connecting edge is constructed between the two vertices.

4. The method according to claim 2, characterized in that, The step of constructing an undirected weighted graph based on the map feature data set specifically includes: For any vertex in the undirected weighted graph, calculate the similarity of map feature attributes between the first map feature corresponding to the vertex and the second map feature corresponding to the vertex; Calculate the importance value of the vertex based on at least one of the category and length of the second map element corresponding to the vertex; The weight value of a vertex is obtained by calculating the product of the similarity of the map element attributes and the importance value.

5. The method according to claim 4, characterized in that, The calculation of the map feature attribute similarity between the first map feature corresponding to the vertex and the second map feature corresponding to the vertex specifically includes: Determine the target attributes of the first map element corresponding to the vertex; For each target attribute, a preset attribute similarity calculation rule corresponding to the type of the target attribute is used to calculate the target attribute similarity. Calculate the average value of the target attribute similarity to obtain the map feature attribute similarity between the first map feature corresponding to the vertex and the second map feature corresponding to the vertex.

6. The method according to claim 5, characterized in that, The step of calculating the target attribute similarity using a preset attribute similarity calculation rule corresponding to the type of the target attribute specifically includes: If the target attribute is a continuous attribute, then the first target attribute similarity is determined based on the map feature similarity between the first map feature corresponding to the vertex and the second map feature corresponding to the vertex; the map feature similarity is positively correlated with the first target attribute similarity. If the target attribute is a discrete attribute, then the second target attribute similarity is determined based on the feature type of the first map feature corresponding to the vertex and the feature type of the second map feature corresponding to the vertex; when the second target attribute similarity is a first preset value, the feature type of the first map feature corresponding to the vertex is the same as the feature type of the second map feature corresponding to the vertex; when the second target attribute similarity is a second preset value, the feature type of the first map feature corresponding to the vertex is different from the feature type of the second map feature corresponding to the vertex.

7. The method according to claim 4, characterized in that, The step of calculating the importance value of a vertex based on at least one of the category and length of the second map feature corresponding to the vertex specifically includes: Determine whether the first map element corresponding to the vertex is a point element; If the first map element corresponding to the vertex is a point element, then the importance value of the vertex is determined to be a third preset value; If the first map feature corresponding to the vertex is not a point feature, then the importance value for the vertex is determined based on the feature length of the second map feature corresponding to the vertex; the feature length of the second map feature corresponding to the vertex is positively correlated with the importance value of the vertex.

8. The method according to claim 1, characterized in that, The step of determining the first target complete subgraph with the largest sum of weight values ​​from the undirected weighted graph specifically includes: Obtain each complete subgraph in the undirected weighted graph; Determine the sum of the weight values ​​of each vertex corresponding to each complete subgraph; From the complete subgraphs, determine the first target complete subgraph with the largest sum of weight values.

9. The method according to claim 8, characterized in that, Obtaining each complete subgraph of the undirected weighted graph specifically includes: For each vertex in the undirected weighted graph, calculate the number of target vertices connected to that vertex; The visiting order of a vertex relative to other vertices in the target set is determined based on the number of target vertices connected to the vertex and the weight value of the vertex; the target set is the set of all the vertices in the undirected weighted graph. Based on the access order, each complete subgraph in the undirected weighted graph is obtained according to each vertex in the target set.

10. The method according to claim 1, characterized in that, After constructing the undirected weighted graph based on the map feature data set, the process further includes: From the undirected weighted graph, a second target complete subgraph is determined; the second target complete subgraph is a complete subgraph of the undirected weighted graph whose sum of weight values ​​is only less than that of the first target complete subgraph. Based on preset evaluation criteria, an evaluation result is obtained for the first target complete sub-map according to the first target complete sub-map and the second target complete sub-map; the evaluation result is used to reflect the difference in the sum of weight values ​​between the first target complete sub-map and the second target complete sub-map, as well as the difference between the number of the first map elements contained in the first target complete sub-map and the number of the first map elements contained in the map acquisition data.

11. The method according to claim 1, characterized in that, The step of determining the map element data set based on the relevant data of the first map element at the target road segment in the map collection data and the relevant data of the second map element at the target road segment in the electronic map data specifically includes: The map data is matched with the electronic map data to determine the driving route of the map data collection device; The driving road is divided into multiple road segments; For any one of the roads, the relevant data of the first map element at any one of the roads in the map collection data and the relevant data of the second map element at any one of the roads in the electronic map data are divided into the map element data set.

12. A device for matching electronic map data with map-collected data, characterized in that, include: The map data acquisition module is used to acquire map data collected by the map data acquisition device; The map element data set determination module is used to determine the map element data set based on the relevant data of the first map element at the target road segment in the map collection data and the relevant data of the second map element at the target road segment in the electronic map data. An undirected weighted graph construction module is used to construct an undirected weighted graph based on the map feature data set. The weight values ​​of the vertices in the undirected weighted graph are used to reflect the similarity between the first map feature corresponding to the vertex and the second map feature corresponding to the vertex. The connecting edges of the undirected weighted graph are used to reflect that the difference between the positional relationships of the map features corresponding to the two vertices of the connecting edge is within a preset difference range. The positional relationship of the map features is the positional relationship between the first map feature corresponding to any vertex and the second map feature corresponding to any vertex. The first target complete subgraph determination module is used to determine the first target complete subgraph with the largest sum of weight values ​​from the undirected weighted graph, and obtain the matching result between the electronic map data and the map collection data. The first target complete subgraph is a complete subgraph of the undirected weighted graph, and there is a connecting edge between any two vertices in the complete subgraph.

13. A device for matching electronic map data with map-collected data, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to: Acquire map data collected by map data acquisition devices; Based on the relevant data of the first map element at the target road segment in the map collection data and the relevant data of the second map element at the target road segment in the electronic map data, a map element data set is determined; Based on the map feature data set, an undirected weighted graph is constructed; the weight values ​​of the vertices in the undirected weighted graph are used to reflect the similarity between the first map feature corresponding to the vertex and the second map feature corresponding to the vertex; the connecting edges of the undirected weighted graph are used to reflect the difference between the positional relationships of the map features corresponding to the two vertices of the connecting edge, which is within a preset difference range; the positional relationship of the map features is the positional relationship between the first map feature corresponding to any vertex and the second map feature corresponding to any vertex; From the undirected weighted graph, the first target complete subgraph with the largest sum of weight values ​​is determined, and the matching result between the electronic map data and the map collection data is obtained. The first target complete subgraph is a complete subgraph of the undirected weighted graph, and there is a connecting edge between any two vertices in the complete subgraph.

Images